Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14940
    Prev
    Next
    INDEX
    Explanations

    terms related to production and manufacturing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HIPAA
    -0.76
    انتهای
    -0.73
    EDEFAULT
    -0.73
    CloseOperation
    -0.72
    ValueStyle
    -0.70
     متعلقه
    -0.70
    ilarang
    -0.67
     CiNii
    -0.66
    uanya
    -0.66
    mantec
    -0.66
    POSITIVE LOGITS
     production
    1.62
     Production
    1.50
     productions
    1.45
    Production
    1.44
    production
    1.40
     produc
    1.34
     PRODUCTION
    1.32
     Prod
    1.27
     produ
    1.23
     produce
    1.20
    Activations Density 0.090%

    No Known Activations